Trevor Slack
Papers
3
Total Citations
13
H-Index
2
About
Trevor Slack is a researcher at the forefront of autonomous systems, specializing in deep reinforcement learning, human-robot trust calibration, and autonomous science planning for planetary exploration. His most cited work, "Generalizing Competency Self-Assessment for Autonomous Vehicles Using Deep Reinforcement Learning" (2022, 9 citations), introduces a novel framework enabling autonomous vehicles to evaluate their own competency in real time. This capability is critical for fostering appropriate human trust in robots operating alongside people in dynamic, high-stakes environments. Slack’s contributions extend to space exploration through his work on "Expert-Informed Autonomous Science Planning for In-situ Observations and Discoveries" (2022, 2 citations) and the "REASON-RECOURSE Software for Science Operations of Autonomous Robotic Landers" (2023, 2 citations). These projects address the challenge of enabling robotic landers on distant bodies like Europa and Enceladus to make independent scientific decisions without human-in-the-loop control, overcoming communication delays and environmental unknowns. By integrating expert knowledge into autonomous planning, Slack is helping to unlock the next generation of deep-space missions. His research is essential reading for anyone interested in trustworthy, self-aware autonomous systems for both terrestrial and extraterrestrial applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3